© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76575
    Prev
    Next
    INDEX
    Explanations

    interracial, interfaith, interspecies, mixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ल्ड
    -0.80
    ctivos
    -0.73
    utel
    -0.70
    rect
    -0.69
    嬢
    -0.68
     carboxylic
    -0.67
    фо
    -0.67
     feminine
    -0.66
    ẞ
    -0.65
    营业
    -0.64
    POSITIVE LOGITS
     inter
    3.42
     mixed
    2.72
    mixed
    2.41
    Mixed
    2.39
    inter
    2.38
     Mixed
    2.34
     bira
    2.14
     меж
    2.09
     Inter
    2.08
    Inter
    2.06
    Activations Density 0.047%

    No Known Activations